| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03422899195618689, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "eval_loss": 1.0124846696853638, | |
| "eval_runtime": 44.6848, | |
| "eval_samples_per_second": 13.763, | |
| "eval_steps_per_second": 6.893, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003422899195618689, | |
| "grad_norm": 0.11466095596551895, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9452, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006845798391237378, | |
| "grad_norm": 0.12092489749193192, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0239, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006845798391237378, | |
| "eval_loss": 1.0004595518112183, | |
| "eval_runtime": 45.1896, | |
| "eval_samples_per_second": 13.609, | |
| "eval_steps_per_second": 6.816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010268697586856067, | |
| "grad_norm": 0.24866552650928497, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9587, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013691596782474755, | |
| "grad_norm": 0.24181249737739563, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8373, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013691596782474755, | |
| "eval_loss": 0.9192121028900146, | |
| "eval_runtime": 45.4474, | |
| "eval_samples_per_second": 13.532, | |
| "eval_steps_per_second": 6.777, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "grad_norm": 0.30564218759536743, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "grad_norm": 0.22930027544498444, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8468, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "eval_loss": 0.8895410299301147, | |
| "eval_runtime": 45.5486, | |
| "eval_samples_per_second": 13.502, | |
| "eval_steps_per_second": 6.762, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023960294369330823, | |
| "grad_norm": 0.22784306108951569, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8522, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02738319356494951, | |
| "grad_norm": 0.2444952130317688, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02738319356494951, | |
| "eval_loss": 0.8780837059020996, | |
| "eval_runtime": 45.8267, | |
| "eval_samples_per_second": 13.42, | |
| "eval_steps_per_second": 6.721, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030806092760568202, | |
| "grad_norm": 0.5582700371742249, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8487, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "grad_norm": 0.22252710163593292, | |
| "learning_rate": 0.0, | |
| "loss": 0.8872, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "eval_loss": 0.8764206767082214, | |
| "eval_runtime": 45.5862, | |
| "eval_samples_per_second": 13.491, | |
| "eval_steps_per_second": 6.756, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.058687007326208e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |